---
base_model:
- KoboldAI/LLaMA2-13B-Psyfighter2
- TeeZee/Orca-2-13b_flat
- KoboldAI/LLaMA2-13B-Erebus-v3
library_name: transformers
tags:
- mergekit
- merge

---
# Psyfighter2-Orca2-Erebus3

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method.

### Models Merged

The following models were included in the merge:
* [KoboldAI/LLaMA2-13B-Psyfighter2](https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2)
* [TeeZee/Orca-2-13b_flat](https://huggingface.co/TeeZee/Orca-2-13b_flat)
* [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: KoboldAI/LLaMA2-13B-Psyfighter2
  - model: TeeZee/Orca-2-13b_flat
    parameters:
      weight: 1.0
      density: 0.4
  - model: KoboldAI/LLaMA2-13B-Erebus-v3
    parameters:
      weight: 1.0
      density: 0.2
merge_method: ties
base_model: KoboldAI/LLaMA2-13B-Psyfighter2
dtype: bfloat16
```